Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: access is gated to callers who can open the organization, it returns "existing: null" on denial, credentials stay server-side, and mailbox passwords/message content are never exposed. This is genuinely useful behavioral disclosure, though it stops short of describing the exact return shape.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is tightly front-loaded with the action first, then return behavior, then access and privacy notes; every fragment carries information. The telegraphic style ("No guest access. Members can read.") is slightly choppy but wastes no words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully sketches the return (org and domain IDs, or existing: null) and covers the authorization model. For a two-parameter read tool with readOnly annotations, this is close to sufficient, missing only the precise return field structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 50% schema coverage, the description must compensate – and it does not. The schema documents organization_id ("Organization ID") but leaves "domain" bare, and the description adds no format guidance (bare domain vs FQDN) or constraints for either parameter, leaving the agent to guess the expected domain syntax.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Find an existing domain" states a recognizable action and the return payload (organization and domain IDs, or null), so the core purpose is legible. However, the name/title say "setup," which implies configuration rather than lookup, and the description never distinguishes this from the sibling commsharbor_email_domain_get. The mismatch plus missing sibling differentiation holds it at a minimum-viable 3.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains permission tiers ("No guest access. Members can read. Owners, admins... can manage") but never states when to pick this tool versus email_domain_get, email_domain_create, or email_domain_verify. There is no when/when-not routing or prerequisite framing, so an agent must infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.